Session 10A Improvements to Subseasonal-to-Seasonal (S2S) Predictions Using Novel Statistical and Artificial Intelligence/Machine Learning (AI/ML) Methods II

Wednesday, 31 January 2024: 10:45 AM-12:00 PM
345/346 (The Baltimore Convention Center)
Host: 23rd Conference on Artificial Intelligence for Environmental Science
Cochairs:
Johnna Infanti, NOAA / NWS / NCEP / Climate Prediction Center, College Park, MD; Nachiketa Acharya; Marybeth Arcodia and Maria J. Molina, AccuWeather, Inc., Office of Organizational Excellence, State College, PA

Subseasonal-to-Seasonal (S2S) forecasting (between two weeks and a season ahead) is a rapidly developing area of forecasting, with the potential to provide valuable information for the development of climate services. Although S2S climate predictions have a comparative lack of skill beyond two-week lead times, over the past decade there has been a substantial research effort to improve prediction skill via novel advanced statistical and Artificial Intelligence/Machine Learning (AI/ML) methods either in terms of post-processing of the dynamical model output or data-driven models based on teleconnections. Additionally, there is a strong interest in understanding predictability on S2S scales using eXplainable Artificial Intelligence (XAI) which could help to improve forecast skill.

This session welcomes all aspects of improving forecasting on S2S scales including advanced statistical and Artificial Intelligence/Machine Learning (AI/ML) based post-processing (bias correction, multi-model ensemble) of the dynamical model output, and ML models based on teleconnections (empirical/data driven). Abstracts that explore XAI for predictability are also encouraged.

Papers:
11:00 AM
10A.2
An Earth-System-Oriented View of the S2S Predictability of Weather Regimes
Jhayron S Perez-Carrasquilla, Univ. of Maryland, College Park, MD; and M. J. Molina

11:15 AM
10A.3
A Deep Learning Approach to Severe Weather Subseasonal Forecasting over the United States
Maria M. Madsen, AI2ES & University of Oklahoma, Norman, OK; and A. McGovern

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner